Triple

T10311271
Position Surface form Disambiguated ID Type / Status
Subject Maryland Route 10 E241894 entity
Predicate abbreviation P43 FINISHED
Object MD 10
MD 10 is a state highway in Maryland that serves as a key connector between Baltimore and its southern suburbs.
E855703 NE FINISHED

How this triple was built (4 steps)

Every LLM step that produced this triple, in pipeline order — named-entity classification, the disambiguation choices (the exact options shown, with the pick highlighted), and the generated description. The batch + timestamp of each is in the Provenance table below.

NER Named-entity recognition gpt-5-mini
Instruction
Given a phrase, classify it is english named entity (e.g., persons, organizations, works of art) in Latin script, or not (e.g., literals, dates, URLs, verbose phrases). For disambiguation, the statement where the phrase occurs as object is also given. Please return a JSON object with `phrase` (string, the phrase being analyzed) and `is_ne` (boolean, indicating whether the phrase is a Named Entity).
Input
Phrase: MD 10 | Statement: [Maryland Route 10, abbreviation, MD 10]
NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07
Target entity: MD 10
Context triple: [Maryland Route 10, abbreviation, MD 10]
  • A. C-10
    C-10 is a commuter rail line within the Cercanías Madrid network that connects central Madrid with its surrounding metropolitan areas.
  • B. M10
    M10 is a major roadway designation used for important motorways or highways in several countries’ transportation networks.
  • C. MD 704
    MD 704 is a state highway in Maryland that serves as a key local connector route in the Washington, D.C. metropolitan area.
  • D. M-50
    M-50 is a major orbital motorway around Madrid, Spain, designed to divert traffic from the city center and connect key suburbs and highways.
  • E. M-46
    M-46 is an east–west state trunkline highway in Michigan that spans much of the state's Lower Peninsula, connecting several communities across multiple counties.
  • F. None of above. chosen
  • G. Unsure - the case is ambiguous/there is not enough information to decide.
NEDg Description generation gpt-5.1
Instruction
Generate a one-sentence description of the target entity. 
You are given a context triple in the form (subject, predicate, object), where the object is the target entity. 
# Instructions
Use the triple to infer relevant information about the entity. Describe the entity based on what is most defining, well-known. 
Avoid repeating the information from the triple, unless really essential.
# Response Format
Return only the sentence: "Description: [one-sentence description of the target entity]"
Input
Entity: MD 10
Triple: [Maryland Route 10, abbreviation, MD 10]
Generated description
MD 10 is a state highway in Maryland that serves as a key connector between Baltimore and its southern suburbs.
NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07
Target entity: MD 10
Target entity description: MD 10 is a state highway in Maryland that serves as a key connector between Baltimore and its southern suburbs.
  • A. C-10
    C-10 is a commuter rail line within the Cercanías Madrid network that connects central Madrid with its surrounding metropolitan areas.
  • B. M10
    M10 is a major roadway designation used for important motorways or highways in several countries’ transportation networks.
  • C. MD 704
    MD 704 is a state highway in Maryland that serves as a key local connector route in the Washington, D.C. metropolitan area.
  • D. M-50
    M-50 is a major orbital motorway around Madrid, Spain, designed to divert traffic from the city center and connect key suburbs and highways.
  • E. M-46
    M-46 is an east–west state trunkline highway in Michigan that spans much of the state's Lower Peninsula, connecting several communities across multiple counties.
  • F. None of above. chosen

Provenance (5 batches)

The batch behind each pipeline step, in order, with when it ran. Timestamps are batch-level — stages were processed in waves, so the object chain (NER → NED1 → NEDg → NED2) reads in order, but predicate / elicitation batches can sit in a different wave.

Step Stage Batch ID Status When
creating Elicitation batch_69d381ac38808190a8ca7457c85b625b completed April 6, 2026, 9:49 a.m.
NER Named-entity recognition batch_69d4d32ac6c08190b23eb042b3ec284a completed April 7, 2026, 9:49 a.m.
NED1 Entity disambiguation (via context triple) batch_69d71d78ece88190885768c979b038df completed April 9, 2026, 3:31 a.m.
NEDg Description generation batch_69d73186831481909555e2205d8783a7 completed April 9, 2026, 4:56 a.m.
NED2 Entity disambiguation (via description) batch_69d732bfc76c819089287477b54a7b77 completed April 9, 2026, 5:01 a.m.
Created at: April 6, 2026, 11:47 a.m.